Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
A novel framework for transferring soft prompts between LLMs while preserving privacy through differential privacy and knowledge distillation techniques.
ICML 2025 ,
| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://stephen016.github.io/publications/
access-control-allow-origin: *
strict-transport-security: max-age=31556952
expires: Tue, 30 Dec 2025 09:20:30 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: F985:3157C7:9C8FA3:B00044:69539706
accept-ranges: bytes
age: 0
date: Tue, 30 Dec 2025 09:10:30 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210070-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767085830.498524,VS0,VE217
vary: Accept-Encoding
x-fastly-request-id: 636f0694ea4ed0a3c77c456a5ea2bf7efee9af63
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Mon, 04 Aug 2025 12:59:43 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"6890aebf-23e0"
expires: Tue, 30 Dec 2025 09:20:30 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: CE49:2F7ECD:9E122D:B18205:69539706
accept-ranges: bytes
age: 0
date: Tue, 30 Dec 2025 09:10:30 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210070-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767085831.744777,VS0,VE218
vary: Accept-Encoding
x-fastly-request-id: c0a52be550f1eefddb9b3bb4c61000d27c49eb5c
content-length: 2841
Publications - Xun Wang - Xun Wang / Personal Page
Publications - Xun Wang
You can also find my articles on my Google Scholar profile.
Structurally Prune Anything: Any Architecture, Any Framework, Any Time
A versatile structured pruning framework that works across any neural network architecture, framework, and training stage, introducing OBSPA for post-training pruning without fine-tuning.
arXiv preprint ,